INDEX

Explanations

locations in California

oai_token-act-pair · gpt-3.5-turbo

mentions of locations in California

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BOOK

-0.82

minded

-0.73

 favour

-0.70

balance

-0.69

schild

-0.68

SHIP

-0.67

usting

-0.67

 denomin

-0.66

chest

-0.63

busters

-0.63

POSITIVE LOGITS

 Calif

1.22

Oro

0.88

erey

0.86

eno

0.84

ano

0.83

illo

0.81

Rim

0.80

Calif

0.78

 Blvd

0.78

 Colo

0.76

Activations Density 0.008%

locations in California

mentions of locations in California

No Comments

No Known Activations